No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Gen-Verse · Agent Tool · ★ 609
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Open-AgentRL safe to install? View the security audit →
RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios RLAnything (click to expand) RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System An overview of our research on RLAnything. In this work, we propose RLAnything, a reinforcement learning framework that dynamically optimizes each component through close
| Stars | 609 |
| Forks | 59 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 64.7509178108662/100 |
| Open Issues | 12 |
| Last Updated | 2026-06-12 |
| Created | 2025-10-13 |
| Platforms | python |
| Est. Tokens | ~13k |
These tools work well together with Open-AgentRL for enhanced workflows:
Looking for a Open-AgentRL alternative? If you're comparing Open-AgentRL with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models
NEWTON: Agentic Planning for Physically Grounded Video Generation
历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.
[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
✨✨Latest Advances on Neuro-Symbolic Learning in the era of Large Language Models
Zero-friction LLM fine-tuning skill for Claude Code, Gemini CLI & any ACP agent. Unsloth on NVIDIA · TRL+MPS/M
Explore other popular agent tool tools:
Open-AgentRL is RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios. It is categorized as a Agent Tool with 609 GitHub stars.
Open-AgentRL is primarily written in Python. It covers topics such as agent-rl, coding-agent, entropy-method.
You can find installation instructions and usage details in the Open-AgentRL GitHub repository at github.com/Gen-Verse/Open-AgentRL. The project has 609 stars and 59 forks, indicating an active community.
Open-AgentRL is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to Open-AgentRL on Agent Skills Hub include llm-rl-environments-lil-course, NEWTON, ICLR2025-Papers-with-Code. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: